Harness Engineering
Source-grounded pack with Agent Runtime Architecture Map, Context and State Contract, and Agent Run Evaluation Harness, plus 1 more.
Use this pack when
Choose this pack when the work touches Harness Engineering and you need a bounded workflow with explicit inputs, a defined output, and human review gates.
Included workflows
Choose the job in front of you.
4 source-grounded skills. Load one workflow at a time.
Agent Runtime Architecture Map
Use this workflow when an agent workflow must move from a good demo or chat prompt into a reproducible runtime with explicit owners, stages, orchestration, context, tools, state, reviews, permissions, logs, failure handling, and learning loops.
Output Return an agent runtime architecture with runspec, stagemap, orchestrationcontract, controllinks, traceandreplay, middlewareboundary, and operatingmodel.
Context and State Contract
Use this workflow when an agent workflow needs an explicit contract for authoritative context, exclusions, provenance, freshness, retrieval, compression, memory, state transitions, checkpoints, invalidation, and safe resumption across long or interrupted runs.
Output Return a context and state contract with contextinventory, precedenceandexclusions, freshnessconflictrules, loadingcompression, statemodel, checkpointschema, and resumptiontests.
Agent Run Evaluation Harness
Use this workflow when an agent workflow needs replayable evaluation of context, decisions, tool calls, state, approvals, outcomes, safety, cost, latency, regressions, and operator learning rather than prompt-quality scores alone.
Output Return an agent evaluation harness specification with evaluationcontract, traceschema, casesuite, scoringrubric, releasethresholds, analysisviews, and learningloop.
Agent Runtime Safety Review
Use this workflow when an agent can call tools, access data, create side effects, or escalate decisions and needs recoverable tool interfaces, least privilege, sandboxes, proportional human review, failure boundaries, readable errors, stop controls, and incident response.
Output Return an agent runtime safety review with actioninventory, toolcontracts, permissionmatrix, failureanalysis, humangatematrix, containmentandrecovery, and testplan.
Human review
Keep consequential decisions explicit.
These workflows structure analysis and artifacts; they do not authorize autonomous external, personnel, financial, legal, security, or other high-impact action.
Source and files
Grounded in the complete Harness Engineering series.
10 source essays · 4 usable skills · reviewed Jul 2026